Metadata-Version: 2.4
Name: agentic-change-log
Version: 0.1.0
Summary: A framework for making agents more aware of their environment through explicit modeling of pre and post effects
Project-URL: Homepage, https://github.com/NaSirMiller/agent-log
License: MIT
Requires-Python: >=3.11
Requires-Dist: numpy
Requires-Dist: pydantic>=2.0
Requires-Dist: scikit-learn
Requires-Dist: sentence-transformers
Description-Content-Type: text/markdown

# Agent-Log

## Overview

Agent-Log is a framework aiming to make agents more aware of their enviroment through the explicit modeling of pre and post effects.
The approach is inspired by logic-based AI theory such as the ["AI Frame Problem"](https://plato.stanford.edu/entries/frame-problem/).

## Repository Overview

This repository implements the Agent-Log framework, providing utility methods that are usable across agentic workflows. Specifically, the following are included:

- Prompt template to ellicit change-logs
- Pre-defined change-log template
  - Currently supports JSON. Future temoplates could include: XML, git diff based
- Extraction methods to decompose set of change-logs from output response to structured objects
- Evaluation or sanity check methods for change-logs
